Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

1,022 builds · page 3 of 18 · clear filters

Devstral-Small-2-24B-Instruct-2512-8bit

from mistralai/Devstral-Small-2-24B-Instruct-2512
8-bit
Vision + text · Mistral ↓ 1.1K · ♥ 2
Params
24B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-04

Unlimited-OCR-2-bf16

from baidu/Unlimited-OCR-2
bf16
Vision + text · baidu ↓ 1.1K · ♥ 7
Params
3.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

mit · updated 2026-10-27

olmOCR-2-7B-1025-mlx-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 1.1K · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-29

gemma-3-27b-it-4bit

from google/gemma-3-27b-pt
4-bit
Vision + text · Google · Gemma ↓ 1.1K · ♥ 13
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-03-19

Qwen3.6-27B-bf16

from Qwen/Qwen3.6-27B
bf16
Vision + text · Qwen ↓ 1.1K · ♥ 7
Params
27B
Weights
≈ 54.7 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-04-22

olmOCR-2-7B-1025-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 1.1K · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-23

Qwen3.5-2B-bf16

from Qwen/Qwen3.5-2B-Base
bf16
Vision + text · Qwen ↓ 1.1K · ♥ 4
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-02

Qwen3.8-27B-nvfp4

from Qwen/Qwen3.8-27B
4-bit
Vision + text · Qwen ↓ 1.1K · ♥ 14
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-11-11

olmOCR-2-7B-1025-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 1.0K · ♥ 2
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-10-22

olmOCR-2-7B-1025-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 1.0K · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-25

PaddleOCR-VL-1.5-bf16

from baidu/ERNIE-4.5-0.3B-Paddle
bf16
Vision + text · baidu ↓ 1.0K · ♥ 6
Params
906M
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-29

MiniMax-M3.1-Flash-oQ3e-mtp

from MiniMaxAI/MiniMax-M3.1-Flash
3-bit
Vision + text · MiniMaxAI ↓ 1.0K · ♥ 4
Params
427B
Weights
≈ 188 GB
Mac memory
256 GB+

minimax-community · updated 2026-10-23

DeepSeek-V4.1-Flash-1017-oQ2e-ngram-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 1.0K · ♥ 3
Params
255B
Weights
≈ 387 GB
Mac memory
512 GB+

mit · updated 2026-10-22

olmOCR-7B-0725-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 1.0K · ♥ 5
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-07-25

Qwen3.5-122B-A10B-6bit

mlx-community/Qwen3.5-122B-A10B-6bit
6-bit
Vision + text ↓ 984 · ♥ 4
Params
123B
Weights
≈ 100 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-02-24

UI-TARS-1.5-7B-4bit

mlx-community/UI-TARS-1.5-7B-4bit
4-bit
Vision + text ↓ 964 · ♥ 2
Params
8.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-25

MiniCPM-V-4.7-35B-A3B-mxfp8

from openbmb/MiniCPM-V-4.7-35B-A3B
MXFP8
Vision + text · openbmb ↓ 962 · ♥ 3
Params
35B
Weights
≈ 39.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-13

MiniCPM-V-4.7-1B-8bit

from openbmb/MiniCPM-V-4.7-1B
8-bit
Vision + text · openbmb ↓ 956 · ♥ 2
Params
1.6B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

Kimi-VL-A3B-Thinking-4bit

from OpenGVLab/InternViT-300M-448px-V2_5
4-bit
Vision + text · OpenGVLab ↓ 951 · ♥ 11
Params
—
Weights
—
Mac memory
—

qwen · updated 2026-01-27

Qwopus3.8-27B-Coder-Flash-8bit

from unsloth/Qwen3.8-27B
8-bit
Vision + text · unsloth ↓ 923 · ♥ 3
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-11-02

MiniCPM-V-4.7-35B-A3B-4bit

from openbmb/MiniCPM-V-4.7-35B-A3B
4-bit
Vision + text · openbmb ↓ 922 · ♥ 0
Params
35B
Weights
≈ 23.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-13

dolphin-vision-72b-4bit

from Qwen/Qwen2-72B
4-bit
Vision + text · Qwen ↓ 921 · ♥ 8
Params
73B
Weights
≈ 41.2 GB
Mac memory
64 GB+

tongyi-qianwen · updated 2024-07-04

Devstral-Small-2-24B-Instruct-2512-6bit

from mistralai/Devstral-Small-2-24B-Instruct-2512
6-bit
Vision + text · Mistral ↓ 914 · ♥ 6
Params
24B
Weights
≈ 20.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-04

Ternary-Bonsai-2-9B-2bit

from Qwen/Qwen3.5-9B
2-bit
Vision + text · Qwen ↓ 897 · ♥ 0
Params
9.4B
Weights
≈ 3.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-15

Qwen3.8-27B-GPTQ-4bit

from Qwen/Qwen3.8-27B
4-bit
Vision + text · Qwen ↓ 891 · ♥ 2
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-11-03

MiniCPM-V-4.7-1B-4bit

from openbmb/MiniCPM-V-4.7-1B
4-bit
Vision + text · openbmb ↓ 886 · ♥ 1
Params
1.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

Muse-Glimmer-30B-mxfp4

from meta-models/Muse-Glimmer-30B
MXFP4
Vision + text · meta-models ↓ 881 · ♥ 0
Params
30B
Weights
≈ 19.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-08-10

PaddleOCR-VL-1.5-8bit

from baidu/ERNIE-4.5-0.3B-Paddle
8-bit
Vision + text · baidu ↓ 874 · ♥ 1
Params
906M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-29

Qwen3.5-397B-A17B-4bit

mlx-community/Qwen3.5-397B-A17B-4bit
4-bit
Vision + text ↓ 853 · ♥ 11
Params
397B
Weights
≈ 224 GB
Mac memory
256 GB+

apache-2.0 · updated 2026-02-18

Qwopus3.8-27B-Coder-Flash-4bit

from unsloth/Qwen3.8-27B
4-bit
Vision + text · unsloth ↓ 833 · ♥ 3
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-11-02

Qwen2.5-VL-32B-Instruct-4bit

mlx-community/Qwen2.5-VL-32B-Instruct-4bit
4-bit
Vision + text ↓ 804 · ♥ 4
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-03-26

medgemma-1.5-4b-it-bf16

mlx-community/medgemma-1.5-4b-it-bf16
bf16
Vision + text ↓ 800 · ♥ 12
Params
5.0B
Weights
≈ 9.9 GB
Mac memory
16 GB+

health-ai-developer-foundations · updated 2026-01-14

MiniCPM-V-4.7-35B-A3B-OptiQ-4bit

from openbmb/MiniCPM-V-4.7-35B-A3B
4-bit
Vision + text · openbmb ↓ 792 · ♥ 3
Params
35B
Weights
≈ 20.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-13

Qwen3.5-122B-A10B-mxfp8

from Qwen/Qwen3.5-122B-A10B
MXFP8
Vision + text · Qwen ↓ 791 · ♥ 0
Params
123B
Weights
≈ 131 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-05-02

SmolVLM2-2.2B-Instruct-mlx

from HuggingFaceTB/SmolVLM2-2.2B-Instruct
Vision + text · Hugging Face ↓ 773 · ♥ 10
Params
2.2B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-20

Qwen3.5-27B-mxfp8

from Qwen/Qwen3.5-27B
MXFP8
Vision + text · Qwen ↓ 772 · ♥ 4
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-03-29

Llama-3.2-90B-Vision-Instruct-4bit

from meta-llama/Llama-3.2-90B-Vision-Instruct
4-bit
Vision + text · Meta · Llama ↓ 770 · ♥ 5
Params
89B
Weights
≈ 49.8 GB
Mac memory
64 GB+

llama3.2 · updated 2024-12-21

gemma-4-e2b-it-8bit

from google/gemma-4-E2B-it
8-bit
Vision + text · Google · Gemma ↓ 767 · ♥ 5
Params
5.1B
Weights
≈ 5.9 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

Qwen3-VL-8B-Instruct-8bit

mlx-community/Qwen3-VL-8B-Instruct-8bit
8-bit
Vision + text ↓ 762 · ♥ 6
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

medgemma-1.5-4b-it-4bit

mlx-community/medgemma-1.5-4b-it-4bit
4-bit
Vision + text ↓ 758 · ♥ 4
Params
5.0B
Weights
≈ 3.4 GB
Mac memory
8 GB+

health-ai-developer-foundations · updated 2026-01-14

Qwen3.6-27B-mxfp8

from Qwen/Qwen3.6-27B
MXFP8
Vision + text · Qwen ↓ 749 · ♥ 5
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-22

North-Mini-Code-1.0-4bit

from CohereLabs/North-Mini-Code-1.0
4-bit
Vision + text · Cohere ↓ 713 · ♥ 3
Params
30B
Weights
≈ 18.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-09

Qwen3.5-122B-A10B-8bit

mlx-community/Qwen3.5-122B-A10B-8bit
8-bit
Vision + text ↓ 701 · ♥ 2
Params
123B
Weights
≈ 131 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-02-24

SmolVLM-Instruct-4bit

from HuggingFaceTB/SmolVLM-Instruct
4-bit
Vision + text · Hugging Face ↓ 696 · ♥ 6
Params
2.2B
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-29

Qwen3-VL-32B-Instruct-4bit

mlx-community/Qwen3-VL-32B-Instruct-4bit
4-bit
Vision + text ↓ 694 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

gemma-4-12B-it-qat-8bit

mlx-community/gemma-4-12B-it-qat-8bit
8-bit
Vision + text ↓ 693 · ♥ 3
Params
12B
Weights
≈ 12.7 GB
Mac memory
24 GB+

updated 2026-06-05

MiniMax-M3.1-Flash-oQ3.5e-mtp

from MiniMaxAI/MiniMax-M3.1-Flash
3-bit
Vision + text · MiniMaxAI ↓ 689 · ♥ 2
Params
427B
Weights
≈ 188 GB
Mac memory
256 GB+

minimax-community · updated 2026-10-23

gemma-4-31b-it-6bit

from google/gemma-4-31B-it
6-bit
Vision + text · Google · Gemma ↓ 683 · ♥ 9
Params
31B
Weights
≈ 26.1 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-05

Qwopus3.8-27B-Coder-Flash-6bit

from unsloth/Qwen3.8-27B
6-bit
Vision + text · unsloth ↓ 660 · ♥ 2
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-11-02

DeepSeek-V4-Pro-Qwen3.5-9B-8bit

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
8-bit
Vision + text · Jackrong ↓ 653 · ♥ 2
Params
9.4B
Weights
≈ 10.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-07

gemma-3-4b-it-bf16

from google/gemma-3-4b-pt
bf16
Vision + text · Google · Gemma ↓ 640 · ♥ 2
Params
5.0B
Weights
≈ 9.9 GB
Mac memory
16 GB+

gemma · updated 2025-03-20

gemma-4-12B-it-6bit

mlx-community/gemma-4-12B-it-6bit
6-bit
Vision + text ↓ 622 · ♥ 2
Params
12B
Weights
≈ 9.7 GB
Mac memory
16 GB+

updated 2026-06-08